Alison's New App is now available on iOS and Android! Download Now

Understanding Visual Matching in Computer Vision

In this free online course, learn about the various visual matching methods in processing images in computer vision.

Publisher: NPTEL
Feature detection and matching are essential components of many computer vision applications. Feature matching is an effective method to detect a specified target in a cluttered scene. This free online course explains the process of selecting an appropriate feature matching strategy for determining the correspondences and the method of devising efficient data structures and algorithms for matching the features.
Understanding Visual Matching in Computer Vision
  • Duration

    1.5-3 Hours
  • Students

  • Accreditation






View course modules


The course introduces the process of establishing preliminary feature matches between two or more images. This includes selecting the appropriate matching strategy for determining which correspondences are passed onto the next stage for further processing and ensuring whether the set of matching features are geometrically consistent. The procedure for devising efficient data structures and algorithms to match the features across different images is explained alongside this. Then the process of isolating features of a particular shape within an image using the Hough transform algorithm is described. You will discover the Hough Transform technique’s significance for having each edge point votes for all possible lines passing through it, and lines corresponding to the high accumulator or bin values are examined for potential line fits.

Next, the course explains how the Hough transform method is used to group edgels into line segments, even across gaps and occlusions in an image. You will be taught about the bag-of-features approach that computes the distribution of visual words found in the query image and compares this distribution to those found in the training images. This explanation will include the process of representing objects and images as disjointed collections of feature descriptors. The process of matching multiple images using selective match kernels are discussed. You will be taught about a match kernel that takes the best of existing techniques by combining an aggregation procedure with a particular match kernel.  The various metrics used for comparing images based on their local descriptors for improving visual recognition of objects, locations and scenes will be investigated. In addition to this, the process of matching kernels for image pyramids are also explained.

Finally, you will explore the methods of mapping unordered feature sets of images to multi-resolution histograms to find implicit correspondences based on the finest resolution histogram cell. This will include the procedure for matching two collections of features in a high-dimensional appearance space. Following on from this, you will discover the significant developments in the field of computer vision over the last few decades. Lastly, the fundamental principles and common pipelines of computer vision that are applied to deep neural networks are highlighted. Understanding Visual Matching in Computer Vision is an informative course, that will interest those studying computer science or those interested in these topics. Why wait? Sign up today and start learning about visual matching methods in the processing of images and the methods of generating efficient and effective visual codebook techniques using additive kernels.

Start Course Now